© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20420
    Prev
    Next
    INDEX
    Explanations

    content body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鹋
    -1.94
     seleccionadas
    -1.76
     欣赏
    -1.73
     favoritas
    -1.66
    鲞
    -1.64
     consideradas
    -1.60
    訁
    -1.60
    蚨
    -1.59
    Werdegang
    -1.58
     fueron
    -1.57
    POSITIVE LOGITS
    If
    1.95
     of
    1.69
    Both
    1.63
    樣子
    1.51
    澳門
    1.50
    與
    1.50
    聖誕
    1.48
     ataupun
    1.46
     Because
    1.45
    鏐
    1.45
    Activations Density 0.011%

    No Known Activations